Climate variables used as response: - sfcWind,
tas, pr: original scale daily,
reduced scale: hourly - clt, rsds:
original scale monthly, reduced scale: daily
Training: All models are trained using ERA5 in reduced scale as observations. Training data perdiod: 1980 - 2015.
Validation Period: 2015-01-02 00:00:00 to 2023-12-30 23:00:00
Response variable to predict: upscaled ERA5 (daily or monthly)
Predictors variables: daily scale the variables
sfcWind, tas, pr,
tasmax, tasmin and psl and in a
monthly scale clt, rsdt,rsds ,
the month , hour, sun’s elevation & azimuth and the daily daylight
amount in seconds.
| Metric | xgboost | cnn | naive | lstm | xgboost_custom |
|---|---|---|---|---|---|
| mae | 0.07 | 0.07 | 0.09 | 0.07 | 0.09 |
| cor | 0.88 | 0.87 | 0.83 | 0.86 | 0.86 |
| ratio_of_sd | 0.86 | 0.93 | 0.81 | 0.87 | 1.01 |
| KGE | 0.81 | 0.78 | 0.69 | 0.80 | 0.56 |
| amplitude_mae | 0.16 | 0.13 | 0.22 | 0.14 | 0.13 |
| maximum_difference | 6.20 | 6.31 | 6.29 | 6.30 | 6.00 |
| sign_correlation | 0.60 | 0.55 | 0.60 | 0.60 | 0.58 |
| extreme_correlation | 0.58 | 0.69 | 0.52 | 0.64 | 0.65 |
| amount_rainy_hours_mae | 1.55 | 1.55 | 2.23 | 1.69 | 2.62 |
| qqplot_mae | 0.02 | 0.02 | 0.04 | 0.02 | 0.05 |
| acf_mae | 0.10 | 0.06 | 0.14 | 0.07 | 0.10 |
| extremogram_mae | 0.06 | 0.03 | 0.07 | 0.03 | 0.05 |
Observations: cumulative distribution (Detrended QQ), dependency structure (ACF), and extremes (Extremogram, using 0.97 cut off).
Daily/Monthly gruped: Maximum hour histogram (only in daily variables), Amplitude distribution.
Hourly/Daily grouped: Mean profile per hour within days (or weeks witihin season)
In all plots, grey color represent the true ERA5 signal.